Embedding Autonomous Agents in Resource-Constrained Robotic Platforms
Negar Halakou, Juan F. Gutierrez, Ye Sun, Han Jiang, Xueming Wu, Yilun Song, Andres Gomez
TL;DR
The paper tackles the challenge of enabling autonomy on resource-constrained robotic platforms by embedding a Belief-Desire-Intention (BDI) agent using the AgentSpeak language within the Embedded-BDI framework. It details a hardware-software co-design where AgentSpeak programs are translated to optimized C++ and executed on a Pololu 3pi+ robot, interfacing through a minimal move API to perform maze navigation with a left-hand rule. Experimental results show the reasoning cycle remains lightweight (belief update, plan selection, and intention execution), with the robot solving a maze in 59 seconds over 287 cycles and consuming modest memory (5.44% Flash, 6.25% RAM). The work demonstrates real-time autonomous operation on MCU-based platforms and points to future multi-robot collaboration by sharing discovered paths via AgentSpeak.
Abstract
Many embedded devices operate under resource constraints and in dynamic environments, requiring local decision-making capabilities. Enabling devices to make independent decisions in such environments can improve the responsiveness of the system and reduce the dependence on constant external control. In this work, we integrate an autonomous agent, programmed using AgentSpeak, with a small two-wheeled robot that explores a maze using its own decision-making and sensor data. Experimental results show that the agent successfully solved the maze in 59 seconds using 287 reasoning cycles, with decision phases taking less than one millisecond. These results indicate that the reasoning process is efficient enough for real-time execution on resource-constrained hardware. This integration demonstrates how high-level agent-based control can be applied to resource-constrained embedded systems for autonomous operation.